Analysis of Localization Using ANN Models in Wireless Sensor Networks

Wireless sensor networks (WSN) usage in numerous applications that increased need has risen to explore more efficient and effective manner. Localization is an important issue that can bring efficiency to WSNs. Localization depicts to calculation of the actual location of unknown nodes in network. This paper focuses on the comparison and analysis of Multi-Layer Perceptron Neural Networks (MLPNN) and Radial Basis Function Neural Networks (RBFNN) for the development of localization framework in WSNs. Using Received Signal Strength Indicator (RSSI) determination of the location a static sensor node on 100 100 m 2 grids from three anchor nodes with fixed positions. The simulation results effectually signify that MLPNN has better localization accuracy as compared to RBFNN.